{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:7DKMRG7UHL67SZZTNYKFNEJNVR","short_pith_number":"pith:7DKMRG7U","canonical_record":{"source":{"id":"1705.10528","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-30T10:07:31Z","cross_cats_sorted":[],"title_canon_sha256":"dbf78666dd68bd85f88be6d02d98078ea570f23da405001333c899c89de0867e","abstract_canon_sha256":"cbcf30b550059314add3371b2a527698292cfddadf18fbe4d96f417b3409beea"},"schema_version":"1.0"},"canonical_sha256":"f8d4c89bf43afdf967336e1456912dac6f9a7431be1ea9ee8f727561f986f394","source":{"kind":"arxiv","id":"1705.10528","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.10528","created_at":"2026-05-18T00:43:24Z"},{"alias_kind":"arxiv_version","alias_value":"1705.10528v1","created_at":"2026-05-18T00:43:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.10528","created_at":"2026-05-18T00:43:24Z"},{"alias_kind":"pith_short_12","alias_value":"7DKMRG7UHL67","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_16","alias_value":"7DKMRG7UHL67SZZT","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_8","alias_value":"7DKMRG7U","created_at":"2026-05-18T12:31:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:7DKMRG7UHL67SZZTNYKFNEJNVR","target":"record","payload":{"canonical_record":{"source":{"id":"1705.10528","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-30T10:07:31Z","cross_cats_sorted":[],"title_canon_sha256":"dbf78666dd68bd85f88be6d02d98078ea570f23da405001333c899c89de0867e","abstract_canon_sha256":"cbcf30b550059314add3371b2a527698292cfddadf18fbe4d96f417b3409beea"},"schema_version":"1.0"},"canonical_sha256":"f8d4c89bf43afdf967336e1456912dac6f9a7431be1ea9ee8f727561f986f394","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:43:24.348332Z","signature_b64":"ViOOWqJl2NeQmidWfCdjknVNXJaOfMLUyiT/2Nw6J/z5QrcoAtPfeJPiM2adbHpuh7W/+iv1EwY2Ow3CJzigCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8d4c89bf43afdf967336e1456912dac6f9a7431be1ea9ee8f727561f986f394","last_reissued_at":"2026-05-18T00:43:24.347799Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:43:24.347799Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1705.10528","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:43:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aY3Hivn7rvAkakljYvBhCvgN7HFG4NU7iGZsV1p7GR+anJXhS/IXImEAd8oma2FW6aew6uPT3DejC4Cq4fxwAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T18:26:20.533381Z"},"content_sha256":"b7bc4c52bc58aafd5024a4cfcc847ddc9b7ddf3065044037dc87262994d48b6d","schema_version":"1.0","event_id":"sha256:b7bc4c52bc58aafd5024a4cfcc847ddc9b7ddf3065044037dc87262994d48b6d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:7DKMRG7UHL67SZZTNYKFNEJNVR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Constrained Policy Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aviv Tamar, David Held, Joshua Achiam, Pieter Abbeel","submitted_at":"2017-05-30T10:07:31Z","abstract_excerpt":"For many applications of reinforcement learning it can be more convenient to specify both a reward function and constraints, rather than trying to design behavior through the reward function. For example, systems that physically interact with or around humans should satisfy safety constraints. Recent advances in policy search algorithms (Mnih et al., 2016, Schulman et al., 2015, Lillicrap et al., 2016, Levine et al., 2016) have enabled new capabilities in high-dimensional control, but do not consider the constrained setting.\n  We propose Constrained Policy Optimization (CPO), the first general"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.10528","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:43:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N4wfYVVMWzHBeSO9zjMuxedpihrabyWnM5jVKFzgu0uy+jCZT+7LnFkqHYOT9yh2OiHxAthu6XNkS7OfpfRSDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T18:26:20.533733Z"},"content_sha256":"e5008aeb3f6f647d2e6156aa7f1e3e9efdecadd1668273d82a806b81d3004ee8","schema_version":"1.0","event_id":"sha256:e5008aeb3f6f647d2e6156aa7f1e3e9efdecadd1668273d82a806b81d3004ee8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7DKMRG7UHL67SZZTNYKFNEJNVR/bundle.json","state_url":"https://pith.science/pith/7DKMRG7UHL67SZZTNYKFNEJNVR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7DKMRG7UHL67SZZTNYKFNEJNVR/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-04T18:26:20Z","links":{"resolver":"https://pith.science/pith/7DKMRG7UHL67SZZTNYKFNEJNVR","bundle":"https://pith.science/pith/7DKMRG7UHL67SZZTNYKFNEJNVR/bundle.json","state":"https://pith.science/pith/7DKMRG7UHL67SZZTNYKFNEJNVR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7DKMRG7UHL67SZZTNYKFNEJNVR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:7DKMRG7UHL67SZZTNYKFNEJNVR","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"cbcf30b550059314add3371b2a527698292cfddadf18fbe4d96f417b3409beea","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-30T10:07:31Z","title_canon_sha256":"dbf78666dd68bd85f88be6d02d98078ea570f23da405001333c899c89de0867e"},"schema_version":"1.0","source":{"id":"1705.10528","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.10528","created_at":"2026-05-18T00:43:24Z"},{"alias_kind":"arxiv_version","alias_value":"1705.10528v1","created_at":"2026-05-18T00:43:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.10528","created_at":"2026-05-18T00:43:24Z"},{"alias_kind":"pith_short_12","alias_value":"7DKMRG7UHL67","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_16","alias_value":"7DKMRG7UHL67SZZT","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_8","alias_value":"7DKMRG7U","created_at":"2026-05-18T12:31:03Z"}],"graph_snapshots":[{"event_id":"sha256:e5008aeb3f6f647d2e6156aa7f1e3e9efdecadd1668273d82a806b81d3004ee8","target":"graph","created_at":"2026-05-18T00:43:24Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"For many applications of reinforcement learning it can be more convenient to specify both a reward function and constraints, rather than trying to design behavior through the reward function. For example, systems that physically interact with or around humans should satisfy safety constraints. Recent advances in policy search algorithms (Mnih et al., 2016, Schulman et al., 2015, Lillicrap et al., 2016, Levine et al., 2016) have enabled new capabilities in high-dimensional control, but do not consider the constrained setting.\n  We propose Constrained Policy Optimization (CPO), the first general","authors_text":"Aviv Tamar, David Held, Joshua Achiam, Pieter Abbeel","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-30T10:07:31Z","title":"Constrained Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.10528","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b7bc4c52bc58aafd5024a4cfcc847ddc9b7ddf3065044037dc87262994d48b6d","target":"record","created_at":"2026-05-18T00:43:24Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"cbcf30b550059314add3371b2a527698292cfddadf18fbe4d96f417b3409beea","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-30T10:07:31Z","title_canon_sha256":"dbf78666dd68bd85f88be6d02d98078ea570f23da405001333c899c89de0867e"},"schema_version":"1.0","source":{"id":"1705.10528","kind":"arxiv","version":1}},"canonical_sha256":"f8d4c89bf43afdf967336e1456912dac6f9a7431be1ea9ee8f727561f986f394","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f8d4c89bf43afdf967336e1456912dac6f9a7431be1ea9ee8f727561f986f394","first_computed_at":"2026-05-18T00:43:24.347799Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:43:24.347799Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ViOOWqJl2NeQmidWfCdjknVNXJaOfMLUyiT/2Nw6J/z5QrcoAtPfeJPiM2adbHpuh7W/+iv1EwY2Ow3CJzigCw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:43:24.348332Z","signed_message":"canonical_sha256_bytes"},"source_id":"1705.10528","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b7bc4c52bc58aafd5024a4cfcc847ddc9b7ddf3065044037dc87262994d48b6d","sha256:e5008aeb3f6f647d2e6156aa7f1e3e9efdecadd1668273d82a806b81d3004ee8"],"state_sha256":"0e8900fa35fd6310e6982897dd3f8e49ac93b7faadb6eb283655b4dcff6f6c46"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ijdLFwwg1qzU1WN4eqTTXALonwB3HXKnusAt7iDSRtY8i6WB36zt+vm2sRxl2wWEYevQQCTmPFKVpXQ66TTzCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T18:26:20.535741Z","bundle_sha256":"7c539ede818fdd05b64a3baab4cb1c3481b8544691f1f050c5b28c80cdfd29b5"}}